Lucene全文检索初识

Lucene 简述
Lucene是一个开放源代码的全文检索引擎工具包，但它不是一个完整的全文检索引擎，而是一个全文检索引擎的架构，提供了完整的查询引擎和索引引擎，部分文本分析引擎。

数据可以三种：

• 结构化数据（具有固定格式或有限长度的数据）
• 非结构化数据
• 半结构化数据

对于结构化数据一般使用SQL语句查询，而非结构化数据有顺序扫描和全文检索。

---

Lucene 文件结构
层次结构：索引 -> 段 -> 文档 -> 域 -> 词
文档是Lucene索引和搜索的原子单位，文档为包括一个或多个域的容器，域则真正包括被搜索的内容，域值通过分词技术处理，得到多个词元。

---

Lucene 索引创建
创建索引的三步：需要检索的数据（Document）、分词技术（Analyzer）、索引创建（indexer）

//创建索引关键类
//IndexWrite
IndexWrite indexWrite=new IndexWrite(directory,indexWriteConfig);
//Directory
Directory directory=FSDirectory.open(new File("C://index));
//Analyzer  创建标准分词器
Analyzer analyzer=new StandardAnalyzer(Version.LUCENE_43);
//Document
Document doc=new Document();
//Filed
doc.add(new TextField("filedname","测试",Store.YES));

Java实现索引创建

package com.lucene;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.*;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;

import java.io.File;
import java.io.IOException;

/**
 * Created with IntelliJ IDEA.
 * User: YEN
 * Date: 2016/8/17
 * Time: 08:26
 */

/**
 * 索引创建
 */
public class IndexCreate {
    public static void main(String[] args) throws IOException {
        //指定分词技术，这里使用的是标准分词
        Analyzer analyzer=new StandardAnalyzer(Version.LUCENE_43);
        //indexWriter的配置信息
        IndexWriterConfig indexWriterConfig=new IndexWriterConfig(Version.LUCENE_43,analyzer);
        //索引的打开方式：没有就创建，有就打开
        indexWriterConfig.setOpenMode(IndexWriterConfig.OpenMode.CREATE_OR_APPEND);
        Directory directory=null;
        IndexWriter indexWriter=null;
        try{
            //确定索引文件的位置 这里是本地文件存储
            directory= FSDirectory.open(new File("C://index"));
            //如果索引处于锁定状态就解锁
            if(indexWriter.isLocked(directory)){
                indexWriter.unlock(directory);
            }
            //指定索引的操作对象为indexWrite
            indexWriter = new IndexWriter(directory, indexWriterConfig);

        }catch ( Exception e ){
            e.printStackTrace();
        }finally {
            indexWriter.close();
            directory.close();
        }

        Document doc1=new Document();
        //StringField域
        doc1.add(new StringField("id","abc", Field.Store.YES));
        //TextField域，采用指定的分词技术
        doc1.add(new TextField("content","Lucene测试", Field.Store.YES));
        //IntField域
        doc1.add(new IntField("num",1, Field.Store.YES));
        //将文档写入到索引中
        indexWriter.addDocument(doc1);

        indexWriter.commit();
    }
}

---

Lucene 索引检索
索引检索的四步：搜索关键字（Keywords）、分词技术（Analyzer）、检索索引（Search）、返回结果。

java实现索引检索

package com.lucene;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.queryparser.classic.ParseException;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;

import java.io.File;
import java.io.IOException;

/**
 * Created with IntelliJ IDEA.
 * User: YEN
 * Date: 2016/8/17
 * Time: 08:42
 */
public class IndexSearch {
    public static void main(String[] args) {
        Directory directory=null;
        try {
            //索引硬盘存储路径
            directory= FSDirectory.open(new File("C://index"));
            //读取索引
            DirectoryReader directoryReader=DirectoryReader.open(directory);
            //创建索引检索对象
            IndexSearcher search=new IndexSearcher(directoryReader);
            //分词技术
            Analyzer analyzer=new StandardAnalyzer(Version.LUCENE_43);
            //创建Query
            QueryParser parser=new QueryParser(Version.LUCENE_43,"content",analyzer);
            Query query=parser.parse("Lucene案例");
            //检索索引，获取符合条件的前10条记录
            TopDocs topDocs=search.search(query,10);
            if(null!=topDocs){
                System.out.println(topDocs.totalHits);
                for ( int i = 0; i < topDocs.scoreDocs.length; i++ ) {
                    Document doc=search.doc(topDocs.scoreDocs[i].doc);
                    System.out.println("id="+doc.get("id"));
                    System.out.println("content="+doc.get("content"));
                }
            }
            directory.close();
            directoryReader.close();
        } catch ( IOException e ) {
            e.printStackTrace();
        } catch ( ParseException e ) {
            e.printStackTrace();
        }
    }
}

---

Lucene 分词器

常用分词器：

• StandardAnalyzer 标准分词器
• IKAnalyzer 基于Lucene的第三方中文分词技术
• WritespaceAnalyzer 空格分词器
• SimpleAnalyzer 简单分词器
• CJKAnalyzer 二分法分词器
• KeywordAnalyzer 关键词分词器
• StopAnalyzer 被忽略词分词器

package com.lucene;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.cjk.CJKAnalyzer;
import org.apache.lucene.analysis.core.KeywordAnalyzer;
import org.apache.lucene.analysis.core.SimpleAnalyzer;
import org.apache.lucene.analysis.core.StopAnalyzer;
import org.apache.lucene.analysis.core.WhitespaceAnalyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.util.Version;
import org.wltea.analyzer.lucene.IKAnalyzer;

import java.io.IOException;
import java.io.StringReader;

/**
 * Created with IntelliJ IDEA.
 * User: YEN
 * Date: 2016/8/17
 * Time: 08:57
 */
public class AnalyzerDemo {
    private static String str="Lucene案例开发";

    public static void main(String[] args) {
        //定义分词器对象
        Analyzer analyzer=null;
        analyzer=new StandardAnalyzer(Version.LUCENE_43);
        AnalyzerDemo.Show(analyzer);
        System.out.println("\n....................................");
        AnalyzerDemo.Show(new IKAnalyzer());
        System.out.println("\n....................................");
        AnalyzerDemo.Show(new WhitespaceAnalyzer(Version.LUCENE_43));
        System.out.println("\n....................................");
        AnalyzerDemo.Show(new SimpleAnalyzer(Version.LUCENE_43));
        System.out.println("\n....................................");
        AnalyzerDemo.Show(new CJKAnalyzer(Version.LUCENE_43));
        System.out.println("\n....................................");
        AnalyzerDemo.Show(new KeywordAnalyzer());
        System.out.println("\n....................................");
        AnalyzerDemo.Show(new StopAnalyzer(Version.LUCENE_43));
    }

    //输出分词结果
    public static void Show(Analyzer analyzer){
        StringReader stringReader=new StringReader(str);
        try {
            TokenStream tokenStream=analyzer.tokenStream("",stringReader);
            tokenStream.reset();
            CharTermAttribute termAttribute=tokenStream.getAttribute(CharTermAttribute.class);
            System.out.println("分词技术："+analyzer.getClass());
            while ( tokenStream.incrementToken() ){
                System.out.print(termAttribute.toString()+"|");
            }

        } catch ( IOException e ) {
            e.printStackTrace();
        }
    }

}